Deep Part Induction from Articulated Object Pairs

by   Li Yi, et al.

Object functionality is often expressed through part articulation -- as when the two rigid parts of a scissor pivot against each other to perform the cutting function. Such articulations are often similar across objects within the same functional category. In this paper, we explore how the observation of different articulation states provides evidence for part structure and motion of 3D objects. Our method takes as input a pair of unsegmented shapes representing two different articulation states of two functionally related objects, and induces their common parts along with their underlying rigid motion. This is a challenging setting, as we assume no prior shape structure, no prior shape category information, no consistent shape orientation, the articulation states may belong to objects of different geometry, plus we allow inputs to be noisy and partial scans, or point clouds lifted from RGB images. Our method learns a neural network architecture with three modules that respectively propose correspondences, estimate 3D deformation flows, and perform segmentation. To achieve optimal performance, our architecture alternates between correspondence, deformation flow, and segmentation prediction iteratively in an ICP-like fashion. Our results demonstrate that our method significantly outperforms state-of-the-art techniques in the task of discovering articulated parts of objects. In addition, our part induction is object-class agnostic and successfully generalizes to new and unseen objects.


page 11

page 13


Self-Supervised Learning of Part Mobility from Point Cloud Sequence

Part mobility analysis is a significant aspect required to achieve a fun...

Parsing Geometry Using Structure-Aware Shape Templates

Real-life man-made objects often exhibit strong and easily-identifiable ...

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes

For the task of mobility analysis of 3D shapes, we propose joint analysi...

Report on the software "SemanticModellingFramework"

The evolution of 3D visual content calls for innovative methods for mode...

Registration Techniques for Deformable Objects

In general, the problem of non-rigid registration is about matching two ...

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

A truly generalizable approach to rigid segmentation and motion estimati...

Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds

We build rearticulable models for arbitrary everyday man-made objects co...

Please sign up or login with your details

Forgot password? Click here to reset